Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 808 750 737 799 668 383 883 652  94 482 344 543 391 283 152  20 582 910 493 474
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1]  20 737 750 383 482 652 582  94 344  NA 543 474 493 152 799 283 910 668 808  NA 391  NA 883
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 3 4 5 5 4 1 5 3 4 4
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "d" "l" "j" "n" "v" "J" "Z" "E" "H" "W"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 18
which( manyNumbersWithNA > 900 )
[1] 17
which( is.na( manyNumbersWithNA ) )
[1] 10 20 22

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 910
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 910
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 910

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "J" "Z" "E" "H" "W"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "d" "l" "j" "n" "v"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE FALSE FALSE FALSE  TRUE FALSE
[19]  TRUE  TRUE
which( manyNumbers %in% 300:600 )
[1]  6 10 11 12 13 17 19 20
sum( manyNumbers %in% 300:600 )
[1] 8

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "large" "large" "small" "small" "large" "large" "small" "small" NA      "large" "small" "small" "small"
[15] "large" "small" "large" "large" "large" NA      "small" NA      "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "large"   "large"   "small"   "small"   "large"   "large"   "small"   "small"   "UNKNOWN" "large"  
[12] "small"   "small"   "small"   "large"   "small"   "large"   "large"   "large"   "UNKNOWN" "small"   "UNKNOWN"
[23] "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0 737 750   0   0 652 582   0   0  NA 543   0   0   0 799   0 910 668 808  NA   0  NA 883

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 3 4 5 1
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  3  4  5  1
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 17
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 910
which.min( manyNumbersWithNA )
[1] 1
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 20
range( manyNumbersWithNA, na.rm = TRUE )
[1]  20 910

Sorting/ordering of vectors

manyNumbersWithNA
 [1]  20 737 750 383 482 652 582  94 344  NA 543 474 493 152 799 283 910 668 808  NA 391  NA 883
sort( manyNumbersWithNA )
 [1]  20  94 152 283 344 383 391 474 482 493 543 582 652 668 737 750 799 808 883 910
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  20  94 152 283 344 383 391 474 482 493 543 582 652 668 737 750 799 808 883 910  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 910 883 808 799 750 737 668 652 582 543 493 482 474 391 383 344 283 152  94  20  NA  NA  NA
manyNumbersWithNA[1:5]
[1]  20 737 750 383 482
order( manyNumbersWithNA[1:5] )
[1] 1 4 5 2 3
rank( manyNumbersWithNA[1:5] )
[1] 1 4 5 2 3
sort( mixedLetters )
 [1] "d" "E" "H" "j" "J" "l" "n" "v" "W" "Z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 4.5 8.0 6.5 1.5 1.5 3.0 9.5 4.5 6.5 9.5
rank( manyDuplicates, ties.method = "min" )
 [1] 4 8 6 1 1 3 9 4 6 9
rank( manyDuplicates, ties.method = "random" )
 [1]  5  8  7  1  2  3  9  4  6 10

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000  0.8974966 -1.0058081 -2.0252153  0.1619413 -0.8163879
[11] -0.2233431  0.2304619  0.7885859 -1.1538665  1.0865769
round( v, 0 )
 [1] -1  0  0  0  1  1 -1 -2  0 -1  0  0  1 -1  1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.9 -1.0 -2.0  0.2 -0.8 -0.2  0.2  0.8 -1.2  1.1
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.90 -1.01 -2.03  0.16 -0.82 -0.22  0.23  0.79 -1.15  1.09
floor( v )
 [1] -1 -1  0  0  1  0 -2 -3  0 -1 -1  0  0 -2  1
ceiling( v )
 [1] -1  0  0  1  1  1 -1 -2  1  0  0  1  1 -1  2

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2022 Biomedical Data Sciences (BDS) | LUMC